docs: refresh dual-mode studio positioning

Author: Wing900

README.md

@@ -27,13 +27,13 @@ English | [简体中文](https://github.com/Wing900/ManimCat/blob/main/README.zh
   </span>
 </p>
 
-<p align="center">
-  <strong>🎬 AI-Powered Mathematical Animation Generator</strong>
-</p>
-
-<p align="center">
-  Making mathematical animation creation simple and elegant, powered by Manim and large language models
-</p>
+<p align="center">
+  <strong>Dual-Mode AI Workspace for Mathematical Visuals</strong>
+</p>
+
+<p align="center">
+  Combining direct workflow generation with agent-driven studio collaboration, powered by Manim and matplotlib
+</p>
 
 <!-- Geometric divider -->
 <div style="margin: 30px 0;">
@@ -67,21 +67,23 @@ English | [简体中文](https://github.com/Wing900/ManimCat/blob/main/README.zh
 
 <br>
 
-## Overview
-
-I am happy to introduce my new project, ManimCat. It is, after all, a cat.
-
+## Overview
+
+I am happy to introduce my new project, ManimCat. It is, after all, a cat.
+
 Built on top of [manim-video-generator](https://github.com/rohitg00/manim-video-generator), ManimCat is now a much broader AI-assisted creation system for math teaching visuals rather than just a single generation flow.
 
-It is designed for classroom explanation, worked-example breakdowns, and visual reasoning tasks. You can use natural language to generate, modify, rerender, and organize Manim-based teaching content with both `video` and `image` outputs.
+It is designed for classroom explanation, worked-example breakdowns, and visual reasoning tasks. You can use natural language to generate, modify, rerender, and organize both animated and static teaching visuals with `video` and `image` outputs.
 
-The project currently has two distinct modes: `Workflow Mode` for direct generation and rendering, and `Agent Mode` for Studio-based collaborative work with longer-lived sessions, review, and iteration.
+The project is now organized around three clear axes: `dual-mode`, `dual-engine`, and `dual-studio`.
+
+- `Workflow Mode` is for direct generation and rendering when you want fast outputs
+- `Agent Mode` is for Studio-based collaborative work with longer-lived sessions, task state, review, and iteration
+- `Manim` is used for animation and timeline-based mathematical storytelling
+- `matplotlib` is used in Plot Studio for static math visuals, charts, and teaching figures
+- `Plot Studio` is the more mature Studio path today for static visual work and iterative editing
+- `Manim Studio` is the animation-oriented Studio path and is still at an earlier stage
 
-- `Workflow Mode` currently supports two direct output paths: `video` and `image`
-- `Agent Mode` currently includes two studios: `Plot Studio` (about 60% complete) and `Manim Studio` (about 20% complete)
-- `Plot Studio` is for matplotlib-based static math visuals, charts, and teaching figures
-- `Manim Studio` is for Manim animation workflows, but it is still at an early stage
-
 ### Interface
 
 #### UI
@@ -143,14 +145,16 @@ If you want a direct Docker deployment path, you can also start from the publish
 
 ## Technology
 
-### Tech Stack
-
-- Product modes: Workflow mode for direct generation, Agent mode for Studio-based collaborative work
-- Backend: Express + TypeScript, Bull + Redis, OpenAI-compatible upstream routing, Studio agent runtime, optional Supabase history storage
-- Frontend: React 19, Vite, Tailwind CSS, classic generator UI, Studio workspace shell
-- Realtime layer: polling for Workflow jobs, Server-Sent Events for Agent sessions, permission requests, and task updates
-- Rendering runtime: Python + Manim Community Edition, LaTeX, `ffmpeg`
-- Deployment: Docker / Docker Compose, Hugging Face Spaces
+### Tech Stack
+
+- Product structure: Workflow mode for direct generation, Agent mode for Studio-based collaborative work
+- Visual engines: Manim for animation, `matplotlib` for Plot Studio static figures
+- Backend: Express + TypeScript, Bull + Redis, OpenAI-compatible upstream routing, Studio agent runtime, optional Supabase history storage
+- Frontend: React 19, Vite, Tailwind CSS, classic generator UI, Studio workspace shell, Plot Studio minimal workspace UI
+- Agent state model: session / run / task / work / result lifecycle for longer-lived studio interactions
+- Realtime layer: polling for Workflow jobs, Server-Sent Events for Agent sessions, permission requests, and task updates
+- Rendering runtime: Python, Manim Community Edition, `matplotlib`, LaTeX, `ffmpeg`
+- Deployment: Docker / Docker Compose, Hugging Face Spaces
 
 ### Workflow Mode
 
@@ -253,14 +257,20 @@ This project is a substantial rework built on top of the original foundation. Th
 - Kept optional multi-profile frontend provider rotation for local use
 - Added optional Supabase-backed persistent history storage
 
-### Studio Agent
-
-- Added a separate Studio mode driven by an agent runtime rather than the classic generation flow
-- Added session, run, task, work, and work-result state models for long-lived agent interactions
-- Added builder, designer, and reviewer roles inside the Studio agent system
-- Added workspace tools, render tools, local skills, and subagent orchestration
-- Added Server-Sent Events for live Studio updates plus permission request / reply handling
-- Added Studio review, pipeline, work, and permission panels in the frontend
+### Studio Agent
+
+- Added a separate Agent Mode driven by a Studio runtime rather than the classic one-shot generation flow
+- Defined the long-lived Studio state model around session / run / task / work / result
+- Added builder, designer, and reviewer roles inside the Studio agent system
+- Added workspace tools, render tools, local skills, and subagent orchestration
+- Added Server-Sent Events for live Studio updates plus permission request / reply handling
+- Added Studio review, pipeline, work, and permission panels in the frontend
+
+### Plot Studio and Manim Studio
+
+- Added two distinct Studio workspaces: Plot Studio for `matplotlib`-based static visuals and Manim Studio for animation-oriented workflows
+- Added Plot Studio output history browsing, work reordering, and a minimal split workspace layout
+- Established the dual-engine product direction: Manim for animated mathematical storytelling, `matplotlib` for static teaching figures and charts
 
 ## License and Copyright
 

README.zh-CN.md

@@ -27,13 +27,13 @@
   </span>
 </p>
 
-<p align="center">
-  <strong>🎬 AI-Powered Mathematical Animation Generator</strong>
-</p>
-
-<p align="center">
-  让数学动画创作变得简单优雅 · 基于 Manim 与大语言模型
-</p>
+<p align="center">
+  <strong>面向数学可视化创作的双模式 AI 工作台</strong>
+</p>
+
+<p align="center">
+  同时支持直接生成工作流与基于 Agent 的 Studio 协作，并由 Manim 与 matplotlib 双引擎支撑
+</p>
 
 <!-- 装饰：几何点阵分隔 -->
 <div style="margin: 30px 0;">
@@ -67,21 +67,23 @@
 
 <br>
 
-## 项目简介
-
-很荣幸在这里介绍我的新项目ManimCat，它是~一只猫~
-
+## 项目简介
+
+很荣幸在这里介绍我的新项目ManimCat，它是~一只猫~
+
 本项目基于 [manim-video-generator](https://github.com/rohitg00/manim-video-generator) 进行了大幅重构与再开发，现在已经不只是单一生成流程，而是一个更完整的 AI 数学教学可视化创作系统。
 
-它面向课堂讲解、例题拆解与数形结合表达等场景，用户可以通过自然语言生成、修改、重渲染并组织基于 Manim 的教学内容，支持 `video` 与 `image` 两种输出。
+它面向课堂讲解、例题拆解与数形结合表达等场景，用户可以通过自然语言生成、修改、重渲染并组织动画与静态两类教学可视化内容，支持 `video` 与 `image` 两种输出。
 
-项目目前包含两种明确区分的模式：`Workflow Mode` 用于直接生成与渲染，`Agent Mode` 用于基于 Studio 的协作式创作、审阅与迭代。
+项目现在可以从三个维度理解：`双模式`、`双引擎`、`双 Studio`。
+
+- `Workflow Mode` 用于直接生成与渲染，适合快速产出
+- `Agent Mode` 用于基于 Studio 的协作式创作、审阅、任务跟踪与迭代
+- `Manim` 负责动画、镜头与时间线驱动的数学叙事
+- `matplotlib` 负责 Plot Studio 中的静态数学图像、函数图、图表与教学插图
+- `Plot Studio` 是目前更成熟的 Studio 路径，主要面向静态可视化与迭代编辑
+- `Manim Studio` 面向动画创作，但目前仍处于相对更早期的阶段
 
-- `Workflow Mode` 当前支持两类直接产出：`video` 和 `image`
-- `Agent Mode` 当前包含两个 Studio：`Plot Studio`（开发程度约 60%）与 `Manim Studio`（开发程度约 20%）
-- `Plot Studio` 面向 matplotlib 静态数学图像、函数图与教学插图
-- `Manim Studio` 面向 Manim 动画工作流，但目前仍处于明显早期阶段
-
 ### 界面
 
 #### UI 界面
@@ -143,14 +145,16 @@ npm run dev
 
 ## 技术
 
-### 技术栈
-
-- 产品模式：Workflow 模式用于直接生成，Agent 模式用于 Studio 协作式工作流
-- 后端：Express + TypeScript、Bull + Redis、兼容 OpenAI 的上游路由、Studio Agent 运行时、可选 Supabase 历史记录
-- 前端：React 19、Vite、Tailwind CSS、经典生成界面、Studio 工作台界面
-- 实时层：Workflow 任务使用轮询，Agent 会话使用 Server-Sent Events 推送事件、权限请求与任务更新
-- 渲染运行时：Python + Manim Community Edition、LaTeX、`ffmpeg`
-- 部署：Docker / Docker Compose、Hugging Face Spaces
+### 技术栈
+
+- 产品结构：Workflow 模式用于直接生成，Agent 模式用于 Studio 协作式工作流
+- 图形引擎：Manim 用于动画，`matplotlib` 用于 Plot Studio 静态图像
+- 后端：Express + TypeScript、Bull + Redis、兼容 OpenAI 的上游路由、Studio Agent 运行时、可选 Supabase 历史记录
+- 前端：React 19、Vite、Tailwind CSS、经典生成界面、Studio 工作台界面、Plot Studio 极简工作区 UI
+- Agent 状态模型：围绕 session / run / task / work / result 组织长生命周期 Studio 交互
+- 实时层：Workflow 任务使用轮询，Agent 会话使用 Server-Sent Events 推送事件、权限请求与任务更新
+- 渲染运行时：Python、Manim Community Edition、`matplotlib`、LaTeX、`ffmpeg`
+- 部署：Docker / Docker Compose、Hugging Face Spaces
 
 ### Workflow Mode
 
@@ -251,14 +255,20 @@ flowchart LR
 - 保留并扩展前端多 profile provider 轮询能力，便于本地使用
 - 新增可选的 Supabase 持久化历史记录存储
 
-### Studio Agent
-
-- 新增独立的 Studio 模式，它不再只是经典生成流程的附属页面，而是单独的 agent 运行模式
-- 新增 session、run、task、work、work result 等长生命周期状态模型
-- 新增 builder、designer、reviewer 三种 Studio agent 角色
-- 新增工作区工具、渲染工具、本地 skills 与子代理编排能力
-- 新增基于 Server-Sent Events 的 Studio 实时更新，以及权限请求 / 回复链路
-- 新增 Studio 前端中的 review、pipeline、work、permission 等面板
+### Studio Agent
+
+- 新增独立的 Agent Mode，它不再只是经典生成流程的附属页面，而是单独的 Studio runtime 工作模式
+- 定义了围绕 session、run、task、work、result 的长生命周期 Studio 状态模型
+- 新增 builder、designer、reviewer 三种 Studio agent 角色
+- 新增工作区工具、渲染工具、本地 skills 与子代理编排能力
+- 新增基于 Server-Sent Events 的 Studio 实时更新，以及权限请求 / 回复链路
+- 新增 Studio 前端中的 review、pipeline、work、permission 等面板
+
+### Plot Studio 与 Manim Studio
+
+- 新增两个明确分化的 Studio 工作区：Plot Studio 面向 `matplotlib` 静态可视化，Manim Studio 面向动画工作流
+- 新增 Plot Studio 的历史产物浏览、工作项重排与极简分栏工作区布局
+- 明确形成双引擎产品方向：Manim 负责动态数学叙事，`matplotlib` 负责静态教学图像与图表
 
 ##  开源与版权声明